Yazar "Subramanian, Thiyagarajan" seçeneğine göre listele
Listeleniyor 1 - 6 / 6
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A deep learning multi-feature based fusion model for predicting the state of health of lithium-ion batteries(Elsevier ltd, 2025) Sonthalia, Ankit; Bai, Femilda Josephin Joseph Shobana; Varuvel, Edwin Geo; Chinnathambi, Arunachalam; Subramanian, Thiyagarajan; Kiani, FarzadLithium-ion batteries have become the preferred energy storage method with applications ranging from consumer electronics to electric vehicles. Utilization of the battery will eventually lead to degradation and capacity fade. Accurately predicting the state of health (SOH) of the cells holds significant importance in terms of reliability and safety of the cell during its operation. The battery degradation mechanism is strongly non-linear and the physics-based model have their inherent disadvantages. The machine learning method has become popular for estimating SOH due to its superior non-linear mapping, adaptive, and self-learning capabilities, made possible by advances in deep learning technologies. In this study parallel hybrid neural network is formulated for predicting the state of health of lithium-ion cell. Firstly, the factors that have an effect on the cell state were analysed. These factors are cell voltage, charging & discharging time and incremental capacity curve. The features were then processed for use as input to the model. Spearman correlation coefficient analysis shows that all the factors had a positive correlation with SOH. While charging time has a negative correlation with the other features. Next the deep learning models namely convolution neural network (CNN), temporal convolution network (TCN), long-short-term memory (LSTM) and bi-directional LSTM were used to make fusion models. The number of layers in CNN and TCN were also varied. The hyperparameters used in the models were optimized using Bayesian optimization algorithm. The models were validated through comparative experiments on the University of Maryland battery degradation dataset. The prediction accuracy with CNN 3-layer LSTM was found to be the best for the training and the test dataset. The overall R2 value, root mean squared error (RMSE) and mean absolute percentage error (MAPE) with the model was found to be 0.999646, 0.003807 and 0.3, respectively. The impact of the features on the model was also analysed by removing one feature and retraining the model with the other features. The effect of discharging time and the peak of the discharge incremental capacity curve was maximum. The analysis also reveals that either charging voltage or discharging voltage can be used. Further, the proposed model was also compared with the other studies. The comparison shows that the R2, RMSE and MAPE values of the proposed model was better.Öğe Comparative analysis to reduce greenhouse gas (GHG) emission in CI engine fuelled with sweet almond oil using ammonia/after treatment system(Elsevier, 2024) Sonthalia, Ankit; Varuvel, Edwin Geo; Subramanian, Thiyagarajan; Josephin, Femilda J. S.; Alahmadi, Tahani Awad; Pugazhendhi, ArivalagaThe present study analyses the various techniques to reduce CO 2 emission, a major contributor to GHG emissions. Diesel was replaced with prunus amygdalus dulcis (sweet almond oil) -fuelled single -cylinder compression ignition (CI) engine. Due to the high viscosity of sweet almond oil, a transesterification procedure was used to convert it to biodiesel. In this experiment, the diesel fuel was entirely substituted with biodiesel (B100) in order to evaluate the emissions, combustion characteristics, and performance of the CI engine operating at a consistent 1500 revolutions per minute under varying loads. In comparison to diesel, tailpipe CO 2 emissions were greater when biodiesel was utilized due to its higher carbon content in the molecular structure. However, plantations absorbs CO 2 emissions from atmosphere causing 'net negative CO 2 emission '. No carbon fuel ammonia was introduced into the intake air using sweet almond oil biodiesel as the base fuel in order to reduce exhaust CO 2 emissions. Under various load conditions, ammonia was introduced at varying flow rates ranging from 10 to 30 LPM. It is observed that increase in ammonia flow rate led to reduction in CO 2 emission. CO 2 emission was reduced from 11.2 % for biodiesel to 6.9 % with 30 LPM ammonia. An after -treatment system was designed with calcite/ activated carbon and retrofitted in exhaust pipe and tested with B100 as fuel. The results indicate that calcite reduces CO 2 more effectively than CO 2 capture systems based on activated carbon. CO 2 emission with calcite is 9.6 % and with activated carbon it is 10.2 % at maximum load condition. The utilization of a calcite -based CO 2 capture system in conjunction with biofuel is believed to effectively mitigate the adverse effects of global warming by generating a net negative CO 2 effect and reducing engine out emissions. Based on the experimental results, compared to after treatment system, ammonia addition with biodiesel is more effective in reducing CO 2 emission without much affecting the other parameters.Öğe Early prediction of the remaining useful life of lithium-ion cells using ensemble and non-ensemble algorithms(John wiley and sons inc, 2025) Bai, Femilda Josephin Joseph Shobana; Sonthalia, Ankit; Subramanian, Thiyagarajan; Aloui, Fethi; Bhatt, Dhowmya; Varuvel, Edwin GeoLithium-ion cells have become an important part of our daily lives. They are used to power mobile phones, laptops and more recently electric vehicles (both two- and four-wheelers). The chemical behavior of the cells is rather complex and non-linear. For reliable and sustainable use of the cells for practical applications, it is imperative to predict the precise pace at which their capacity will degrade. More importantly, the lifetime of the cells must be predicted at an early stage, which would accelerate development and design optimization of the cells. However, most of the existing methods cannot predict the lifetime at an early stage, since there is a weak correlation between the cell capacity and lifetime. In this study for accurate forecasting of the battery lifetime, the patterns of the parameters such as cell current, voltage, temperature, charging time, internal resistance, and capacity were examined during charging and discharging cycle of the cell. Twelve manually crafted features were prepared from these parameters. The dataset for the features was created using the raw data of the first 100 cycles of 124 cells. Six ensemble and non-ensemble machine learning algorithms, namely, multiple linear regression (MLR), decision tree, support vector machine (SVM), gradient boosting machine (GBM), light gradient boosting machine (LGBM), and extreme gradient boosting (XGBoost), were trained with the features for predicting the life-cycle of the cells. The R2 and root mean squared error (RMSE) values of MLR, decision tree, SVM, GBM, LGBM, and XGBoost were found to be 0.72 and 201, 0.83 and 155, 0.85 and 146, 0.92 and 100, 0.9 and 112, and 0.94 and 95, respectively. The prediction accuracy of lithium-ion cell life-time was found to be the best with the XGBoost algorithm. This shows that only first 100 cycles are required foraccurately predicting the number of cycles the lithium-ion cell can work for. Lastly, the results of the study were compared with the available studies in the literature. Three studies were chosen, and the RMSE of the method proposed in this study was found to be higher than the three studies by 43, 17, and 20. Therefore, the proposed method is a suitable option for predicting the lifetime of lithium-ion cells during the early stages of its development.Öğe Effect of amyl alcohol addition in a CI engine with Prosopis juliflora oil - an experimental study(Taylor and Francis, 2021) Duraisamy, Boopathi; Velmurugan, Kandasamy; Venkatachalapathy, V. S.Karuppannan; Subramanian, Thiyagarajan; Varuvel, Edwin GeoThis study aims to replace diesel with Prosopis Juliflora seed oil (JPO) in a compression ignition (CI) engine. The high viscosity of JPO promotes inferior performance and combustion. Brake thermal efficiency of JPO is 28.3%, which is less compared to 30.7% for diesel. This also leads to higher brakespecific energy consumption, HC, CO, and smoke emissions. JPO was converted to its biodiesel (Prosopis Juliflora methyl ester) (JPME) through the transesterification process. The physical properties were improved posttransesterification process. Brake thermal efficiency was improved to 29.3% for JPME. Higher NOx emission with reduced HC, CO, and smoke emissions was observed with JPME in comparison with JPO. The test engine employed for the investigations has a single-cylinder configuration with the maximum power of 5.2 kW enabled with water cooling. Furthermore, amyl alcohol was added with JPME in various proportions of 5%, 10%, 15%, and 20% by volume and experiments were conducted. The addition of amyl alcohol in the volume mentioned earlier has improved the thermal efficiency at higher loads; added to this NO and smoke emission were lowered simultaneously for all the loading conditions. Except with the 5% volume of amyl alcohol, HC and CO emissions have increased for all other volume compositions. JPME with 20% volume amyl alcohol exhibits the highest peak pressure and heat release rate. The brake thermal efficiency of JPME + A20 is on par with diesel. NO and smoke were reduced by 7% and 29%, respectively, for JPME + A20 in comparison with diesel. The study shows that the addition of 20% amyl alcohol with JPME has performance and emission characteristics similar to diesel. Further increase in amyl alcohol led to poor cold starting condition and may also lead to knocking. Hence, it was concluded to use only up to 20% of amyl alcohol to avoid any operational complications.Öğe Experimental investigation of ammonia gas as hydrogen carrier in prunus amygdalus dulcis oil fueled compression ignition engine(Elsevier Ltd, 2024) Sonthalia, Ankit; Geo Varuvel, Edwin; Subramanian, Thiyagarajan; Josephin JS, Femilda; Almoallim, Hesham S.; Pugazhendhi, ArivalaganThe present study aims to utilize ammonia gas as a hydrogen carrier with prunus amygdalus dulcis (sweet almond oil)-fueled single-cylinder compression ignition (CI) engine. Due to the high viscosity of sweet almond oil, a transesterification procedure was used to convert it to biodiesel. The diesel fuel was completely replaced with biodiesel to assess the performance, emission, and combustion characteristics of the CI engine running at a constant speed of 1500 rpm under different load conditions. Poor performance and combustion were exhibited with biodiesel in comparison to diesel. Lower brake thermal efficiency with higher fuel consumption and lower nitrous oxides (NOx) emissions were observed with biodiesel in comparison to diesel. While hydrocarbon (HC), carbon monoxide (CO), and smoke emissions were higher with biodiesel, to further improve the performance, hydrogen gas was introduced at different flow rates (10–30 LPM). Hydrogen improved the brake thermal efficiency with reduced carbon emissions. At maximum load condition, with 30 LPM hydrogen brake thermal efficiency is improved by 15 %. However, NOx emissions were higher with hydrogen induction compared to base fuels at all load conditions. NOx emissions were increased from 1274 ppm with biodiesel to 1451 ppm with 30 LPM hydrogen addition at maximum load. Although hydrogen is one of the most promising techniques to improve the performance of biodiesel, its higher NOx emissions and safety aspects make its practical application questionable. Hence, ammonia gas was used as a hydrogen carrier, and tests were conducted in dual fuel mode with biodiesel at different flow rates. It is observed that performance parameters in ammonia dual fuel mode are on par with those of biodiesel with reduced carbon and NOx emissions. Hence, ammonia can be considered a viable option to replace hydrogen as its carrier to meet global energy demands and also for its safer use. © 2024 Elsevier LtdÖğe Moving ahead from hydrogen to methanol economy: scope and challenges(Springer Science and Business Media Deutschland GmbH, 2021) Sonthalia, Ankit; Kumar, Naveen; Tomar, Mukul; Varuvel, Edwin Geo; Subramanian, Thiyagarajan; Pugazhendhi, ArivalaganAbstract: Energy is the driver in the economic development of any country. However, most of the developing countries do not have sufficient oil reserves to cater to their energy requirement and depend upon oil producing countries. The perturbations in the crude oil price and adverse environmental impacts from fossil fuel usage are the biggest concern. Therefore, developing countries have started investing heavily in solar and wind power and are considering hydrogen as a future energy resource. However, to tap the potential of hydrogen as a fuel, an entirely new infrastructure will be needed for transporting, storing and dispensing it safely, which would be expensive. In the transportation sector, a liquid alternate to fossil fuels will be highly desirable as the existing infrastructure can be used with minor modifications. Among the possible liquid fuels, methanol is very promising. Methanol is a single carbon atom compound and can be produced from wide variety of sources such as natural gas, coal and biomass. The properties of methanol are conducive for use in gasoline engines since it has high octane number and flame speed. Other possible uses of methanol are: as a cooking fuel in rural areas and as a fuel for running the fuel cells. The present study reviews the limitations in the hydrogen economy and why moving toward methanol economy is more beneficial. Graphic Abstract: [Figure not available: see fulltext.]
